© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27207
    Prev
    Next
    INDEX
    Explanations

    copyright year "5"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ../../../
    -0.10
    宵
    -0.09
    olem
    -0.09
    usch
    -0.09
     Loving
    -0.09
    ìĤ¼
    -0.08
    éĢĤæŶ
    -0.08
    è¿Ļ两ç§į
    -0.08
    æĮĩå°İ
    -0.08
    欹
    -0.08
    POSITIVE LOGITS
    деÑģÑıÑĤ
    0.14
    деÑģÑı
    0.14
    0.13
    -HT
    0.13
    teenth
    0.12
    fold
    0.11
    -star
    0.11
    -Star
    0.11
    nier
    0.11
    th
    0.11
    Activations Density 0.634%

    No Known Activations